Is there a way to access the audio clip that gets used for Google's speech-to-text transcribing?

I've been getting increasingly inaccurate output using Google's speech-to-text output. After discovering my Samsung phone has more than one microphone, I'm wondering if perhaps this could have to do with either which microphone is getting used, and/or if there's any audio processing being applied which is affecting accuracy.

If I could debug these waveform/recordings myself, I could at least see whether the input itself is the source of the inaccuracy, or whether it's something else.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.